Refactor eeg

Author: chkoar

imblearn/ensemble/easy_ensemble_generalization.py

@@ -5,16 +5,15 @@
 # License: MIT
 
 import numpy as np
-
 from sklearn.base import ClassifierMixin, clone
-from sklearn.ensemble import BaseEnsemble, VotingClassifier
+from sklearn.ensemble import VotingClassifier
+from sklearn.ensemble.base import BaseEnsemble, _set_random_states
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.utils import check_random_state
 from sklearn.utils.validation import check_is_fitted
 
 from ..pipeline import Pipeline
-from ..under_sampling import RandomUnderSampler as ROS
-
+from ..under_sampling import RandomUnderSampler
 
 MAX_INT = np.iinfo(np.int32).max
 
@@ -101,7 +100,7 @@ def _validate_sampler(self):
         if self.base_sampler is not None:
             self.base_sampler_ = self.base_sampler
         else:
-            self.base_sampler_ = ROS()
+            self.base_sampler_ = RandomUnderSampler()
 
         if self.base_sampler_ is None:
             raise ValueError("base_sampler cannot be None")
@@ -136,27 +135,18 @@ def fit(self, X, y, sample_weight=None):
         self._validate_sampler()
 
         random_state = check_random_state(self.random_state)
-        estimator_seeds = random_state.randint(MAX_INT, size=self.n_estimators)
-        sampler_seeds = random_state.randint(MAX_INT, size=self.n_estimators)
 
         if not hasattr(self.base_sampler, 'random_state'):
             ValueError('Base sampler must have a random_state parameter')
 
-        pipelines = []
-        seeds = zip(estimator_seeds, sampler_seeds)
-
-        for i, (estimator_seed, sampler_seed) in enumerate(seeds):
-
-            sampler = clone(self.base_sampler_)
-            sampler.set_params(random_state=sampler_seed)
+        steps = [('sampler', self.base_sampler_),
+                 ('estimator', self.base_estimator_)]
+        pipeline_template = Pipeline(steps)
 
-            if hasattr(self.base_estimator_, 'random_state'):
-                estimator = clone(self.base_estimator_)
-                estimator.set_params(random_state=estimator_seed)
-            else:
-                estimator = clone(self.base_estimator_)
-            steps = [('sampler', sampler), ('estimator', estimator)]
-            pipeline = Pipeline(steps)
+        pipelines = []
+        for i in enumerate(range(self.n_estimators)):
+            pipeline = clone(pipeline_template)
+            _set_random_states(pipeline, random_state)
             pipelines.append(pipeline)
 
         ensemble_members = [[str(i), pipeline]

imblearn/ensemble/tests/test_easy_ensemble_generalization.py

@@ -50,7 +50,7 @@ def test_majority_label():
     eeg = EEG(voting='soft', random_state=RND_SEED)
     scores = cross_val_score(eeg, X, y, cv=5, scoring='roc_auc')
     print(scores.mean())
-    assert_almost_equal(scores.mean(), 0.625, decimal=2)
+    assert_almost_equal(scores.mean(), 0.65, decimal=2)
 
 
 def test_predict_on_toy_problem():